You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@iceberg.apache.org by GitBox <gi...@apache.org> on 2021/05/27 09:58:48 UTC
[GitHub] [iceberg] rymurr commented on a change in pull request #2613: Hive: Vectorized ORC reads for Hive
rymurr commented on a change in pull request #2613:
URL: https://github.com/apache/iceberg/pull/2613#discussion_r640465542
##########
File path: build.gradle
##########
@@ -551,6 +551,60 @@ project(':iceberg-mr') {
}
if (jdkVersion == '8') {
+ // The purpose of this module is to re-shade org.apache.orc.storage to the original org.apache.hadoop.hive package
+ // name. This is to be used by Hive3 for features including e.g. vectorization.
+ project(':iceberg-hive3-orc-bundle') {
Review comment:
how does this compare to the original hive bundle? Do we need to support both? Apologies if thats a dumb question, I am just not 100% sure I understand what will be in this resulting bundle and who will use it.
##########
File path: mr/src/main/java/org/apache/hadoop/hive/ql/exec/vector/VectorizedSupport.java
##########
@@ -0,0 +1,45 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.hadoop.hive.ql.exec.vector;
+
+import java.util.HashMap;
+import java.util.Map;
+
+/**
+ * Copied here from Hive for compatibility
+ */
+@SuppressWarnings({"Indentation", "WhitespaceAfter", "VisibilityModifier"})
Review comment:
Same as previous comment
##########
File path: hive3/src/main/java/org/apache/iceberg/mr/hive/vector/CompatibilityHiveVectorUtils.java
##########
@@ -0,0 +1,300 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.iceberg.mr.hive.vector;
+
+import java.sql.Date;
+import java.sql.Timestamp;
+import org.apache.commons.lang3.StringUtils;
+import org.apache.hadoop.hive.common.type.HiveDecimal;
+import org.apache.hadoop.hive.common.type.HiveIntervalDayTime;
+import org.apache.hadoop.hive.common.type.HiveIntervalYearMonth;
+import org.apache.hadoop.hive.ql.exec.Utilities;
+import org.apache.hadoop.hive.ql.exec.tez.DagUtils;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.ColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.IntervalDayTimeColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector;
+import org.apache.hadoop.hive.ql.plan.BaseWork;
+import org.apache.hadoop.hive.ql.plan.MapWork;
+import org.apache.hadoop.hive.serde2.io.DateWritable;
+import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+/**
+ * Contains ported code snippets from later Hive sources. We should get rid of this class as soon as Hive 4 is released
+ * and Iceberg makes a dependency to that version.
+ */
+public class CompatibilityHiveVectorUtils {
+
+ private static final Logger LOG = LoggerFactory.getLogger(CompatibilityHiveVectorUtils.class);
+
+ private CompatibilityHiveVectorUtils() {
+
+ }
+
+ /**
+ * Returns serialized mapwork instance from a job conf - ported from Hive source code LlapHiveUtils#findMapWork
+ *
+ * @param job JobConf instance
+ * @return
+ */
+ @SuppressWarnings("Slf4jConstantLogMessage")
+ public static MapWork findMapWork(JobConf job) {
+ String inputName = job.get(Utilities.INPUT_NAME, null);
+ if (LOG.isDebugEnabled()) {
+ LOG.debug("Initializing for input " + inputName);
+ }
+ String prefixes = job.get(DagUtils.TEZ_MERGE_WORK_FILE_PREFIXES);
+ if (prefixes != null && !StringUtils.isBlank(prefixes)) {
+ // Currently SMB is broken, so we cannot check if it's compatible with IO elevator.
+ // So, we don't use the below code that would get the correct MapWork. See HIVE-16985.
+ return null;
+ }
+
+ BaseWork work = null;
+ // HIVE-16985: try to find the fake merge work for SMB join, that is really another MapWork.
+ if (inputName != null) {
+ if (prefixes == null || !Lists.newArrayList(prefixes.split(",")).contains(inputName)) {
+ inputName = null;
+ }
+ }
+ if (inputName != null) {
+ work = Utilities.getMergeWork(job, inputName);
+ }
+
+ if (!(work instanceof MapWork)) {
+ work = Utilities.getMapWork(job);
+ }
+ return (MapWork) work;
+ }
+
+
+ /**
+ * Ported from Hive source code VectorizedRowBatchCtx#addPartitionColsToBatch
+ *
+ * @param col ColumnVector to write the partition value into
+ * @param value partition value
+ * @param partitionColumnName partition key
+ * @param rowColumnTypeInfo column type description
+ */
+ @SuppressWarnings({"AvoidNestedBlocks", "FallThrough", "MethodLength", "CyclomaticComplexity", "Indentation"})
Review comment:
Any chance that instead of porting ropey code into iceberg we could write this better and upstream the change?
##########
File path: hive3/src/main/java/org/apache/iceberg/mr/hive/vector/CompatibilityHiveVectorUtils.java
##########
@@ -0,0 +1,300 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.iceberg.mr.hive.vector;
+
+import java.sql.Date;
+import java.sql.Timestamp;
+import org.apache.commons.lang3.StringUtils;
+import org.apache.hadoop.hive.common.type.HiveDecimal;
+import org.apache.hadoop.hive.common.type.HiveIntervalDayTime;
+import org.apache.hadoop.hive.common.type.HiveIntervalYearMonth;
+import org.apache.hadoop.hive.ql.exec.Utilities;
+import org.apache.hadoop.hive.ql.exec.tez.DagUtils;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.ColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.IntervalDayTimeColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.TimestampColumnVector;
+import org.apache.hadoop.hive.ql.plan.BaseWork;
+import org.apache.hadoop.hive.ql.plan.MapWork;
+import org.apache.hadoop.hive.serde2.io.DateWritable;
+import org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo;
+import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.iceberg.relocated.com.google.common.collect.Lists;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+/**
+ * Contains ported code snippets from later Hive sources. We should get rid of this class as soon as Hive 4 is released
+ * and Iceberg makes a dependency to that version.
+ */
+public class CompatibilityHiveVectorUtils {
+
+ private static final Logger LOG = LoggerFactory.getLogger(CompatibilityHiveVectorUtils.class);
+
+ private CompatibilityHiveVectorUtils() {
+
+ }
+
+ /**
+ * Returns serialized mapwork instance from a job conf - ported from Hive source code LlapHiveUtils#findMapWork
+ *
+ * @param job JobConf instance
+ * @return
+ */
+ @SuppressWarnings("Slf4jConstantLogMessage")
Review comment:
Why suppress the warning instead of fixing the issue?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org